Downloads · 30 days
7
19% of all-time downloads
dianavdavidson/wav2vec2-xls-r-1b-iv_hindi_vaani-62414-hinglish_mixed_scripts-alldata-1e-4-epochs-100-mix-0.5-FT
wav2vec2-xls-r-1b-iv_hindi_vaani-62414-hinglish_mixed_scripts-alldata-1e-4-epochs-100-mix-0.5-FT is a automatic speech recognition model from dianavdavidson. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
7
19% of all-time downloads
All-time downloads
36
Public
Parameters
963M
3.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.9 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Global Wer |
|---|---|---|---|---|
| 2.0876 | 1.0 | 1080 | 0.8737 | 51.5890 |
| 1.5012 | 2.0 | 2160 | 0.7309 | 43.7930 |
| 1.2046 | 3.0 | 3240 | 0.6851 | 39.4289 |
| 0.9815 | 4.0 | 4320 | 0.7130 | 37.6894 |
| 0.8459 | 5.0 | 5400 | 0.7023 | 36.7049 |
| 0.7517 | 6.0 | 6480 | 0.7321 | 35.5040 |
| 0.6044 | 7.0 | 7560 | 0.7545 | 36.2460 |
| 0.5485 | 8.0 | 8640 | 0.7386 | 35.6586 |
| 0.4933 | 9.0 | 9720 | 0.7759 | 35.4780 |
| 0.4403 | 10.0 | 10800 | 0.7732 | 34.5716 |
| 0.3931 | 11.0 | 11880 | 0.7824 | 34.7311 |
| 0.3636 | 12.0 | 12960 | 0.8216 | 35.2909 |
| 0.3236 | 13.0 | 14040 | 0.7959 | 34.0379 |
| 0.3011 | 14.0 | 15120 | 0.8118 | 34.7929 |
| 0.2767 | 15.0 | 16200 | 0.8209 | 34.6969 |
| 0.2630 | 16.0 | 17280 | 0.8588 | 34.9752 |